CT-Based Radiomics to Predict <i>KRAS</i> Mutation in CRC Patients Using a Machine Learning Algorithm: A Retrospective Study
Jacobo Porto-Álvarez,
Eva Cernadas,
Rebeca Aldaz Martínez,
Manuel Fernández-Delgado,
Emilio Huelga Zapico,
Víctor González-Castro,
Sandra Baleato-González,
Roberto García-Figueiras,
J Ramon Antúnez-López,
Miguel Souto-Bayarri
Affiliations
Jacobo Porto-Álvarez
Department of Radiology, Complexo Hospitalario Universitario de Santiago de Compostela, 15706 Santiago de Compostela, Spain
Eva Cernadas
Centro Singular de Investigación en Tecnoloxías Intelixentes da USC (CiTIUS), Universidade de Santiago de Compostela, 15705 Santiago de Compostela, Spain
Rebeca Aldaz Martínez
Department of Radiology, Complexo Hospitalario Universitario de Santiago de Compostela, 15706 Santiago de Compostela, Spain
Manuel Fernández-Delgado
Centro Singular de Investigación en Tecnoloxías Intelixentes da USC (CiTIUS), Universidade de Santiago de Compostela, 15705 Santiago de Compostela, Spain
Emilio Huelga Zapico
Department of Radiology, Complexo Hospitalario Universitario de Santiago de Compostela, 15706 Santiago de Compostela, Spain
Víctor González-Castro
Department of Electrical, Systems and Automation Engineering, Universidad de León, 24071 León, Spain
Sandra Baleato-González
Department of Radiology, Complexo Hospitalario Universitario de Santiago de Compostela, 15706 Santiago de Compostela, Spain
Roberto García-Figueiras
Department of Radiology, Complexo Hospitalario Universitario de Santiago de Compostela, 15706 Santiago de Compostela, Spain
J Ramon Antúnez-López
Department of Pathology, Complexo Hospitalario Universitario de Santiago de Compostela, 15706 Santiago de Compostela, Spain
Miguel Souto-Bayarri
Department of Radiology, Complexo Hospitalario Universitario de Santiago de Compostela, 15706 Santiago de Compostela, Spain
Colorectal cancer (CRC) is one of the most common types of cancer worldwide. The KRAS mutation is present in 30–50% of CRC patients. This mutation confers resistance to treatment with anti-EGFR therapy. This article aims at proving that computer tomography (CT)-based radiomics can predict the KRAS mutation in CRC patients. The piece is a retrospective study with 56 CRC patients from the Hospital of Santiago de Compostela, Spain. All patients had a confirmatory pathological analysis of the KRAS status. Radiomics features were obtained using an abdominal contrast enhancement CT (CECT) before applying any treatments. We used several classifiers, including AdaBoost, neural network, decision tree, support vector machine, and random forest, to predict the presence or absence of KRAS mutation. The most reliable prediction was achieved using the AdaBoost ensemble on clinical patient data, with a kappa and accuracy of 53.7% and 76.8%, respectively. The sensitivity and specificity were 73.3% and 80.8%. Using texture descriptors, the best accuracy and kappa were 73.2% and 46%, respectively, with sensitivity and specificity of 76.7% and 69.2%, also showing a correlation between texture patterns on CT images and KRAS mutation. Radiomics could help manage CRC patients, and in the future, it could have a crucial role in diagnosing CRC patients ahead of invasive methods.